🔍 AgentLens

Open-source observability for AI agents — with a tamper-evident audit trail
_{Every event SHA-256 hash-chained & cryptographically verifiable — built for EU AI Act Article 12 record-keeping}

📖 Documentation · Quick Start · Dashboard · ☁️ Cloud

---

📑 Table of Contents

• Tamper-Evident by Design
• Quick Start
• Architecture
• Integration Guides
• Key Features
• Dashboard
• AgentLens Cloud
• Packages
• API Overview
• CLI
• Development
• Contributing
• AgentKit Ecosystem
• License

---

AgentLens is a flight recorder for AI agents. It captures every LLM call, tool invocation, approval decision, and error — then presents it through a queryable API and real-time web dashboard.

🔒 Tamper-evident by design

What sets AgentLens apart from other observability tools: every event is SHA-256 hash-chained to the one before it, the same way git commits and blockchains are linked. The audit log is append-only and cryptographically verifiable — alter, delete, or reorder a single record after the fact and verification fails, pointing at the exact event that broke. Purpose-built for the record-keeping obligations of EU AI Act Article 12 and the emerging IETF Agent Audit Trail work.

See it for yourself in 30 seconds (needs Docker):

git clone https://github.com/agentkitai/agentlens && cd agentlens
./demo/aha.sh

1/5  Starting AgentLens (SQLite, zero-config)…   ✓ up at http://localhost:3400
2/5  Ingesting a 5-event agent trace…            ✓ 5 events ingested
3/5  Verifying the hash chain…                    ✓ CHAIN VALID — no tampering detected
4/5  Tampering with one event in the database…   ✓ altered llm_call (changed the logged model)
5/5  Re-verifying the hash chain…                 ✗ CHAIN BROKEN — tampering detected ✅

The demo ingests a real trace, verifies the chain (passes), edits one record directly in the database behind the audit log's back, then re-verifies (fails). Auditors get a signed, verifiable JSON snapshot from GET /api/audit/verify/export.

Five ways to integrate — pick what fits your stack:

Integration	Language	Effort	Capture
🔭 OpenTelemetry	Any	Point your OTLP exporter	Any gen_ai.*-instrumented agent — no AgentLens SDK
🤖 OpenClaw Plugin	OpenClaw	Copy & enable	Every Anthropic call — prompts, tokens, cost, tools — zero code
🐍 Python Auto-Instrumentation	Python	1 line	Every OpenAI / Anthropic / LangChain call — deterministic
🔌 MCP Server	Any (MCP)	Config block	Tool calls, sessions, events from Claude Desktop / Cursor
📦 SDK	Python, TypeScript	Code	Full control — log events, query analytics, build integrations

🚀 Quick Start

One command — server + dashboard on SQLite, zero config:

docker run -p 3400:3400 -e AUTH_DISABLED=true -e JWT_SECRET=dev-secret ghcr.io/agentkitai/agentlens
# Open http://localhost:3400

Or without Docker:

npx @agentkitai/agentlens-server
# http://localhost:3400 with SQLite — zero config

AUTH_DISABLED=true is for a quick local trial (JWT_SECRET is still required by the hardened image). For anything shared, drop AUTH_DISABLED, set a real JWT_SECRET, and create an API key (below).

Full stack (Postgres + Redis, auth, TLS) — runs from source:

git clone https://github.com/agentkitai/agentlens && cd agentlens
cp .env.example .env
docker compose up
# production overlay (auth, restart policies):
docker compose -f docker-compose.yml -f docker-compose.prod.yml up

Create an API Key

curl -X POST http://localhost:3400/api/keys \
  -H "Content-Type: application/json" \
  -d '{"name": "my-agent"}'

Save the als_... key from the response — it's shown only once. Then head to the Integration Guides to instrument your agent.

📖 Full setup guide →

🏗️ Architecture

graph TB
    subgraph Agents["Your AI Agents"]
        PY["Python App<br/>(OpenAI, Anthropic, LangChain)"]
        MCP_C["MCP Client<br/>(Claude Desktop, Cursor)"]
        TS["TypeScript App"]
        OC["OpenClaw Plugin"]
    end

    PY -->|"agentlensai.init()<br/>auto-instrumentation"| SERVER
    MCP_C -->|MCP Protocol| MCP_S["@agentkitai/agentlens-mcp"]
    MCP_S -->|HTTP| SERVER
    TS -->|"@agentkitai/agentlens-sdk"| SERVER
    OC -->|HTTP| SERVER

    subgraph Server["@agentkitai/agentlens-server"]
        direction TB
        INGEST[Ingest Engine]
        QUERY[Query Engine]
        ALERT[Alert Engine]
        LLM_A[LLM Analytics]
        HEALTH[Health Scoring]
        COST[Cost Optimizer]
        REPLAY[Session Replay]
        BENCH[Benchmark Engine]
        GUARD[Guardrails]
    end

    SERVER --> DB[(SQLite / Postgres)]
    SERVER --> DASH["Dashboard<br/>(React SPA)"]

    EXT["AgentGate / FormBridge"] -->|Webhook| SERVER

🔧 Integration Guides

🔭 OpenTelemetry (any GenAI agent — no SDK)

If your agent is already instrumented with the OpenTelemetry GenAI semantic conventions — via OpenLLMetry, OpenInference, or the official OTel instrumentations — just point its OTLP exporter at AgentLens. No AgentLens SDK required.

# Send standard OTLP/HTTP to AgentLens (JSON or protobuf, /v1/traces)
export OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:3400
export OTEL_EXPORTER_OTLP_TRACES_ENDPOINT=http://localhost:3400/v1/traces

AgentLens maps gen_ai.* spans into its model and into the tamper-evident audit log:

OTel GenAI span (gen_ai.operation.name)	Becomes
chat / text_completion / generate_content	a paired llm_call + llm_response (model, provider, messages, usage.input_tokens/output_tokens, finish reason, latency, cost)
execute_tool	tool_call (gen_ai.tool.name, gen_ai.tool.call.id, arguments)
embeddings	embedding event with token usage
invoke_agent / create_agent	agent-invocation event

Each OTel trace maps to a session (or gen_ai.conversation.id if present), and every event is hash-chained like any other — so traces from any GenAI framework get the same verifiable audit trail. Set OTLP_AUTH_TOKEN to require a bearer token on the OTLP endpoints in production.

Cost with no SDK: OTel GenAI instrumentation reports tokens but rarely cost. AgentLens reconstructs costUsd from the model's per-1M-token pricing (fuzzy-matched on the model id), so OTel-only agents get the same cost analytics as SDK-instrumented ones — no per-call cost attribute required.

🤖 OpenClaw Plugin

If you're running OpenClaw, the AgentLens plugin captures every Anthropic API call automatically — prompts, completions, token usage, costs, latency, and tool calls.

cp -r packages/relay-plugin /usr/lib/node_modules/openclaw/extensions/agentlens-relay
openclaw config patch '{"plugins":{"entries":{"agentlens-relay":{"enabled":true}}}}'
openclaw gateway restart

Set AGENTLENS_URL if your AgentLens instance isn't on localhost:3400. See the plugin README for details.

🐍 Python Auto-Instrumentation

One line — every LLM call captured automatically across 9 providers (OpenAI, Anthropic, LiteLLM, AWS Bedrock, Google Vertex AI, Google Gemini, Mistral AI, Cohere, Ollama):

pip install agentlensai[all-providers]

import agentlensai

agentlensai.init(
    url="http://localhost:3400",
    api_key="als_your_key",
    agent_id="my-agent",
)
# Every LLM call is now captured automatically

Key guarantees: ✅ Deterministic · ✅ Fail-safe · ✅ Non-blocking · ✅ Privacy (init(redact=True))

📖 Python SDK full docs →

🔌 MCP Integration

For Claude Desktop, Cursor, or any MCP client — add to your config:

{
  "mcpServers": {
    "agentlens": {
      "command": "npx",
      "args": ["@agentkitai/agentlens-mcp"],
      "env": {
        "AGENTLENS_API_URL": "http://localhost:3400",
        "AGENTLENS_API_KEY": "als_your_key_here"
      }
    }
  }
}

AgentLens ships 22 MCP tools — covering core observability, intelligence & analytics, and operations. Full MCP tool reference →

📖 MCP setup guide →

📦 Programmatic SDK

Python:

pip install agentlensai

from agentlensai import AgentLensClient
client = AgentLensClient("http://localhost:3400", api_key="als_your_key")
sessions = client.get_sessions()
analytics = client.get_llm_analytics()

TypeScript:

npm install @agentkitai/agentlens-sdk

import { AgentLensClient } from '@agentkitai/agentlens-sdk';
const client = new AgentLensClient({ baseUrl: 'http://localhost:3400', apiKey: 'als_your_key' });
const sessions = await client.getSessions();

📖 SDK reference →

✨ Key Features

• 🐍 Python Auto-Instrumentation — agentlensai.init() captures every LLM call across 9 providers automatically. Deterministic — no reliance on LLM behavior.
• 🔌 MCP-Native — Ships as an MCP server. Works with Claude Desktop, Cursor, and any MCP client.
• 🔭 OpenTelemetry GenAI — Ingests gen_ai.* OTLP traces from any OTel-instrumented agent (OpenLLMetry, OpenInference, official OTel) — no AgentLens SDK required.
• 🧠 LLM Call Tracking — Full prompt/completion visibility, token usage, cost aggregation, latency measurement, and privacy redaction.
• 📊 Real-Time Dashboard — Session timelines, event explorer, LLM analytics, cost tracking, and alerting.
• 🔒 Tamper-Evident Audit Trail — Append-only event storage with SHA-256 hash chains per session.
• 💰 Cost Tracking — Track token usage and estimated costs per session, per agent, per model. Alert on cost spikes.
• 🚨 Alerting — Configurable rules for error rate, cost threshold, latency anomalies, and inactivity.
• ❤️‍🩹 Health Scores — 5-dimension health scoring with trend tracking.
• 💡 Cost Optimization — Complexity-aware model recommendation engine with projected savings.
• 📼 Session Replay — Step-through any past session with full context reconstruction.
• ⚖️ A/B Benchmarking — Statistical comparison of agent variants using Welch's t-test and chi-squared analysis.
• 🛡️ Guardrails — Automated safety rules with dry-run mode for safe testing.
• 🔌 Framework Plugins — LangChain, CrewAI, AutoGen, Semantic Kernel — auto-detection, fail-safe, non-blocking.
• 🔗 AgentKit Ecosystem — Integrations with AgentGate, FormBridge, Lore, and AgentEval.
• 🔒 Tenant Isolation — Multi-tenant support with per-tenant data scoping and API key binding.
• 🏠 Self-Hosted — SQLite by default, no external dependencies. MIT licensed.

📸 Dashboard

AgentLens ships with a real-time web dashboard for monitoring your agents.

📸 Dashboard Screenshots (click to expand)

Overview — At-a-Glance Metrics

The overview page shows live metrics — sessions, events, errors, and active agents — with a 24-hour event timeline chart, recent sessions with status badges, and a recent errors feed.

Sessions — Track Every Agent Run

Every agent session with sortable columns: agent name, status, start time, duration, event count, error count, and total cost.

Session Detail — Timeline & Hash Chain

Full event timeline with tamper-evident hash chain verification. Filter by event type, view cost breakdown.

Events Explorer — Search & Filter Everything

Searchable, filterable view of every event across all sessions.

🧠 LLM Analytics — Prompt & Cost Tracking

Total LLM calls, cost, latency, and token usage across all agents with model comparison.

🧠 Session Timeline — LLM Call Pairing

LLM calls in session timeline with model, tokens, cost, and latency.

💬 Prompt Detail — Chat Bubble Viewer

Full prompt and completion in a chat-bubble style viewer with metadata panel.

❤️‍🩹 Health Overview — Agent Reliability

5-dimension health score for every agent with trend tracking.

💡 Cost Optimization — Model Recommendations

Analyzes LLM call patterns and recommends cheaper model alternatives with confidence levels.

📼 Session Replay — Step-Through Debugger

Step through any past session event by event with full context reconstruction.

⚖️ Benchmarks — A/B Testing for Agents

Create and manage A/B experiments with statistical significance testing.

🛡️ Guardrails — Automated Safety Rules

Create and manage automated safety rules with trigger history and activity feed.

☁️ AgentLens Cloud

Don't want to self-host? AgentLens Cloud is a fully managed SaaS — same SDK, zero infrastructure:

import agentlensai
agentlensai.init(cloud=True, api_key="als_cloud_your_key_here", agent_id="my-agent")

• Same SDK, one parameter change — switch url= to cloud=True
• Managed Postgres — multi-tenant with row-level security
• Team features — organizations, RBAC, audit logs
• No server to run — dashboard at app.agentlens.ai

📖 Cloud Setup Guide · Migration Guide · Troubleshooting

📦 Packages

Python (PyPI)

Package	Description	PyPI
agentlensai	Python SDK + auto-instrumentation for 9 LLM providers

TypeScript / Node.js (npm)

Package	Description	npm
@agentkitai/agentlens-server	Hono API server + dashboard serving
@agentkitai/agentlens-mcp	MCP server for agent instrumentation
@agentkitai/agentlens-sdk	Programmatic TypeScript client
@agentkitai/agentlens-core	Shared types, schemas, hash chain utilities
@agentkitai/agentlens-cli	Command-line interface
@agentkitai/agentlens-dashboard	React web dashboard (bundled with server)	private

🔌 API Overview

Endpoint	Description
POST /api/events	Ingest events (batch)
GET /api/events	Query events with filters
GET /api/sessions	List sessions
GET /api/sessions/:id/timeline	Session timeline with hash chain verification
GET /api/analytics	Bucketed metrics over time

Full API Reference →

⌨️ CLI

npx @agentkitai/agentlens-cli health                          # Overview of all agents
npx @agentkitai/agentlens-cli health --agent my-agent          # Detailed health with dimensions
npx @agentkitai/agentlens-cli optimize                          # Cost optimization recommendations

Both commands support --format json for machine-readable output. See agentlens health --help for all options.

🛠️ Development

git clone https://github.com/agentkitai/agentlens.git
cd agentlens
pnpm install

pnpm typecheck && pnpm test && pnpm lint  # Run all checks
pnpm dev                                   # Start dev server

Requirements: Node.js ≥ 20.0.0 · pnpm ≥ 10.0.0

🤝 Contributing

We welcome contributions! See CONTRIBUTING.md for setup instructions, coding standards, and the PR process.

🧰 AgentKit Ecosystem

Project	Description
AgentLens	Observability & tamper-evident audit trail for AI agents	⬅️ you are here
AgentGate	Human-in-the-loop approval gateway + reactive guardrails
Lore	Cross-agent memory and lesson sharing
AgentEval	Testing & evaluation framework
FormBridge	Agent-human mixed-mode forms

📄 License

MIT © Amit Paz